Search
ciplogo
ciplogotype
4th International Workshop on Cognitive Information Processing

May 26-28, 2014     Bella Sky Hotel, Copenhagen, Denmark

Multimodal Imaging, Non-stationarity and Brain-Computer Interfacing
Klaus-Robert Müller Professor Klaus-Robert Müller
Department of Software Engineering and Theoretical Computer Science, TU Berlin, Germany
Personal homepage
Download lecture slides

Biography:

Klaus-Robert Müller (CV) received the Diploma degree in mathematical physics in 1989 and the Ph.D. in theoretical computer science in 1992, both from University of Karlsruhe, Germany. From 1992 to 1994 he worked as a Postdoctoral fellow at GMD FIRST, in Berlin where he started to built up the intelligent data analysis (IDA) group. From 1994 to 1995 he was a European Community STP Research Fellow at University of Tokyo in Prof. Amari's Lab. From 1995 until 2008 he was head of department of the IDA group at GMD FIRST (since 2001 Fraunhofer FIRST) in Berlin and since 1999 he holds a joint associate Professor position of GMD and University of Potsdam. In 2003 he became a full professor at University of Potsdam, in 2006 he became chair of the machine learning department at TU Berlin. He has been lecturing at Humboldt University, Technical University Berlin and University of Potsdam. In 1999 he received the annual national prize for pattern recognition (Olympus Prize) awarded by the German pattern recognition society DAGM and in 2006 the SEL Alcatel communication award. He serves in the editorial boards of Computational Statistics, IEEE Transactions on Biomedical Engineering, Journal of Machine Learning Research and in program and organization committees of various international conferences.(services) His research areas include statistical learning theory for neural networks, support vector machines and ensemble learning techniques. He contributed to the field of signal processing working on time-series analysis, statistical denoising methods and blind source separation. His present application interests are expanded to the analysis of biomedical data, most recently to brain computer interfacing and genomic data analysis.

Abstract:

Learning to build universal decoders for brain-computer interfaces (BCIs) is a great challenge. Usually in multimodal imaging we consider the modes to be different types of imaging devices such as EEG, NIRS or fMRI. However, we can also interpret different subjects as imaging modalities to gain a zero training decoder from a data base of subjects. Even the same subject data from several experiments can be seen as instantiations of multiple modes. The talk will discuss recent multimodal analysis techniques such as SPoC. Furthermore we will discuss non-stationarities that often occur in neuroscience, e.g. between a subject's training and testing session in brain-computer interfacing. We show that such changes can be very similar between subjects, and thus can be reliably estimated using data from other users and utilized to construct an invariant feature space. These insights can be accumulated into a broader theoretical framework using beta divergences. We show that it can not only achieve a significant increase in performance, but also that the extracted change patterns allow for a neurophysiologically meaningful interpretation.

A Cognitive Architecture for Object Recognition in Video
Jose Principe Professor Jose C. Principe
BellSouth Professor and Director, Computational NeuroEngineering Lab, University of Florida, USA
Personal homepage
Download lecture slides

Biography:

Jose C. Principe (M'83-SM'90-F'00) is a Distinguished Professor of Electrical and Computer Engineering and Biomedical Engineering at the University of Florida where he teaches advanced signal processing, machine learning and artificial neural networks (ANNs) modeling. He is BellSouth Professor and the Founder and Director of the University of Florida Computational NeuroEngineering Laboratory (CNEL) www.cnel.ufl.edu . His primary area of interest is processing of time varying signals with adaptive neural models. The CNEL Lab has been studying signal and pattern recognition principles based on information theoretic criteria (entropy and mutual information).

Dr. Principe is an IEEE Fellow. He was the past Chair of the Technical Committee on Neural Networks of the IEEE Signal Processing Society, Past-President of the International Neural Network Society, and Past-Editor in Chief of the IEEE Transactions on Biomedical Engineering. He is a member of the Advisory Board of the University of Florida Brain Institute. Dr. Principe has more than 500 publications. He directed 78 Ph.D. dissertations and 65 Master theses. He wrote in 2000 an interactive electronic book entitled "Neural and Adaptive Systems" published by John Wiley and Sons and more recently co-authored several books on "Brain Machine Interface Engineering" Morgan and Claypool, "Information Theoretic Learning", Springer, and "Kernel Adaptive Filtering", Wiley.

Abstract:

This talk describes our efforts to abstract from the animal visual system the computational principles to explain images in video. We develop a hierarchical, distributed architecture of dynamical systems that self-organizes to explain the input imagery using an empirical Bayes criterion with sparseness constraints and dual state estimation. The interpretation of the images is mediated through causes that flow top down and change the priors for the bottom up processing. We will present preliminary results in several data sets.

Exploratory and Contextual Search with Interactive Intent Modelling
Samuel Kaski Professor Samuel Kaski
Aalto University and University of Helsinki, Finland
Personal homepage
Download lecture slides

Biography:

Samuel Kaski is a full Professor of Computer Science at Aalto University, the director of Helsinki Institute for Information Technology HIIT, Aalto University and University of Helsinki, the Chairman of the Board of Directors of CSC - IT Center for Science, and a group leader in Biocentrum Helsinki. He got his D.Sc. (PhD) in computer science in Helsinki University of Technology in 1997. At the moment he is an action editor of JMLR and the programme committee chairman of AISTATS, and serves in the programme committees of several other conferences. He develops machine learning methods, in particular for learning from multiple data sources and information visualization. The main application fields are computational systems biology and medicine, proactive information retrieval, and multimodal interfaces. He has published 194 peer-reviewed papers on these topics.

Abstract:

We develop methods for improving information seeking by interactive intent modelling, and have demonstrated the methods with two systems. SciNet is an interactive search system for scientific documents, in which the user directs the search by giving feedback for estimated search intents. In the current version of SciNet the potential intents are represented by keywords and laid out on an "intent radar" display which visualizes both their estimated relevances and similarity. Probabilistic language modelling and reinforcement learning are combined with new visualization methods for search in over 50 million scientific documents, outperforming conventional searches in user experiments. The other system is a prototype augmented reality (AR) platform for accessing abstract information in real-world pervasive computing environments. The user's interests with respect to the environment are inferred from eye movement patterns, speech, and other implicit feedback signals, and these data are used for information filtering. The results of proactive context-sensitive information retrieval are augmented onto the view of a handheld or head-mounted display or uttered as synthetic speech. The augmented information becomes part of the user's context, and if the user shows interest in the AR content, the system detects this and provides progressively more information.

Sensory Analysis - A Research Paradigm for Linking Perception and Physics/Signal Processing
Søren Bech Head of Research, Professor Søren Bech
Bang and Olufsen A/S and Aalborg University, Denmark
Personal homepage
Download lecture slides

Biography:

Søren Bech received a M.Sc. and a Ph.D. from the Department of Acoustic Technology (AT) of the Technical University of Denmark. From 1982 - 92 he was research Fellow at AT studying perception and evaluation of reproduced sound in small rooms. In 1992 he joined Bang & Olufsen where he is Head of Research. In 2011 he was appointed Professor in Audio Perception at Aalborg University and he is Adjunct Professor at Aarhus University (DK), Surrey University (GB), and McGill University (CAN). He has been PI (either entirely or for B&O's part) in 15 international research projects and is a Fellow of the Acoustical Society of America and Audio Engineering Society (AES). He is past Governor and Vice-President of the AES and now serves as associate technical editor of the AES Journal. He has been vice-chair of the International Telecommunication Union working group 10/3. In 2006 he and Dr. Zacharov published the book "Perceptual Audio Evaluation - Theory, Method and Application" (Wiley and Sons). His research interest includes psychoacoustics and in particular human perception of reproduced sound in small and medium sized rooms. Other interests include experimental procedures and statistical analysis of data from sensory analysis of audio and video quality.

Abstract:

Signal processing is present and has a significant role in the daily life of almost all human beings - from ordinary domestic appliances like a TV or radio to echo cancellation in mobile phones, compression of audio and video signals, search engines for music and video and music databases and so on and so on….and constantly increasing processing power makes for an almost endless list of possible applications. But, and this is a significant "but", almost everybody has experienced a situation where all the possibilities for control/adjustment/calibration is of no benefit to the user either because it is impossible for the user to understand what is going on or because the "processing" does not benefit the specific intentions or context of the user. The missing link is often a basic knowledge of the relationship between the physics of the introduced changes and the human perception of those changes. The study of the relationship between changes in the physical world and the corresponding changes in human perception is the science called "psychophysics" or sensory science in a broader context. The purpose of this talk is to introduce sensory analysis as a research paradigm and further to illustrate how it's applied in Bang & Olufsen's product development.
Powered by CONWIZ, © Copyright 2013. Page maintained by Jan Larsen (Email)